tldr_keywords / app.py
vanessbut's picture
Исправлен spacy.
720e187
raw
history blame
968 Bytes
import streamlit as st
st.markdown("""### TL;DR: give me the keywords!
Here you can get the keywords and topic of the article based on it's title or abstract.""")
st.markdown("<p style=\"text-align:center\"><img width=700px src='https://c.tenor.com/IKt-6tAk9CUAAAAd/thats-a-lot-of-words-lots-of-words.gif'></p>", unsafe_allow_html=True)
#from transformers import pipeline
#pipe = pipeline("ner", "Davlan/distilbert-base-multilingual-cased-ner-hrl")
#st.markdown("#### Title:")
title = st.text_area("Title:")
abstract = st.text_area("abstract:")
from utils.utils import *
import spacy
import en_core_web_sm
# Вообще, стоит найти pipeline, заточенный под научный текст.
# Но этим займёмся потом, если будет время.
#main_nlp = spacy.load('en_core_web_sm')
main_nlp = en_core_web_sm.load()
text = title + abstract
#text = preprocess(text)
st.markdown(f"{get_candidates(text, main_nlp)}")